161 citations · 235 across the 16 of their papers we have counts for
18 papers
From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations
Dimitris Michailidis, Petter Törnberg, Fernando P. Santos
Generative Social Simulation (GSS) leverages Large Language Models (LLMs) to create sophisticated personas that define agents with demographics, emotions, and political opinions. W…
Meeting the Coming Wave: The Emerging Politics of AI and Work across 33 Parliaments
Juliana Chueri, Petter Törnberg
A new politics of artificial intelligence and work is taking shape across party systems, but comparative politics has yet to map it. Using 1,514,950 parliamentary speeches from 33…
Political Sorting Can Drive AI Models Apart Through User Feedback
Petter Törnberg, Michael Heseltine, Nicolò Pagan +3
Large language models are rapidly becoming an important source of political information. This raises a fundamental question: will AI systems support a shared basis for political kn…
The Politics Attention Makes: Platform Media Logic and the Mediatization of Politics
Petter Törnberg
Empirical research on social media and politics has primarily treated platforms as distributive systems that expose users to particular messages. The mediatization literature, howe…
Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor
Petter Törnberg, Michelle Schimmel
Large language models (LLMs) are commonly evaluated for political bias based on their responses to fixed questionnaires, which typically place frontier models on the political left…
Polarization by Default: Auditing Recommendation Bias in LLM-Based Content Curation
Nicolò Pagan, Christopher Barrie, Chris Andrew Bail +1
Large Language Models (LLMs) are increasingly deployed to curate and rank human-created content, yet the nature and structure of their biases in these tasks remains poorly understo…
Large Language Models Reproduce Racial Stereotypes When Used for Text Annotation
Petter Törnberg
Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation and hiring. Across 19 LLMs and two ex…
Shifts in U.S. Social Media Use, 2020-2024: Decline, Fragmentation, and Enduring Polarization
Petter Törnberg
Using nationally representative data from the 2020 and 2024 American National Election Studies (ANES), this paper traces how the U.S. social media landscape has shifted across plat…
Online Homogeneity Can Emerge Without Filtering Algorithms or Homophily Preferences
Petter Törnberg
Ideologically homogeneous online environments - often described as "echo chambers" or "filter bubbles" - are widely seen as drivers of polarization, radicalization, and misinformat…
Can We Fix Social Media? Testing Prosocial Interventions using Generative Social Simulation
Maik Larooij, Petter Törnberg
Social media platforms have been widely linked to societal harms, including rising polarization and the erosion of constructive debate. Can these problems be mitigated through pros…
Measuring Negative Campaigning across Languages with Large Language Models: A Study of 18 Million Tweets in 19 Countries
Victor Hartman, Petter Törnberg
Negative campaigning is a defining feature of electoral competition, yet comparative research on its drivers has remained limited by the high cost and limited scalability of existi…
Elite political incivility is rising across democracies
Petter Törnberg, Juliana Chueri
Is political incivility rising across democracies - and if so, why? Analysing approximately 13.8 million tweets from parliamentarians in 26 countries with a validated large languag…
Prompt Stability Scoring for Text Annotation with Large Language Models
Christopher Barrie, Elli Palaiologou, Petter Törnberg
Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a given output according to a set o…
Best Practices for Text Annotation with Large Language Models
Petter Törnberg
Large Language Models (LLMs) have ushered in a new era of text annotation, as their ease-of-use, high accuracy, and relatively low costs have meant that their use has exploded in r…
Toxic Bias: Perspective API Misreads German as More Toxic
Gianluca Nogara, Francesco Pierri, Stefano Cresci +3
Proprietary public APIs play a crucial and growing role as research tools among social scientists. Among such APIs, Google's machine learning-based Perspective API is extensively u…
Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithms
Petter Törnberg, Diliara Valeeva, Justus Uitermark +1
Social media is often criticized for amplifying toxic discourse and discouraging constructive conversations. But designing social media platforms to promote better conversations is…
How to use LLMs for Text Analysis
Petter Törnberg
This guide introduces Large Language Models (LLM) as a highly versatile text analysis method within the social sciences. As LLMs are easy-to-use, cheap, fast, and applicable on a b…
ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning
Petter Törnberg
This paper assesses the accuracy, reliability and bias of the Large Language Model (LLM) ChatGPT-4 on the text analysis task of classifying the political affiliation of a Twitter p…